Artificial intelligence in endodontics: relevant trends and practical perspectives
Open Access
- 5 March 2023
- journal article
- research article
- Published by Ukrainian Public Scientific Society "Continuing Dental Education" in Ukrainian Dental Journal
- Vol. 2 (1) , 96-101
Abstract
Background. Overall pool of studies regarding artificial intelligence (AI) implementation in dentistry is increasing every year, while possibilities for using AI methods within everyday endodontic practice is still quite confined and not always enough affirmed. Objective. To systematize and depict principal data regarding use of virtual artificial intelligence for various endodontic-related clinical purposes. Materials and Methods. Targeted literature search was provided within National Center for Biotechnology Information databases using pre-specified Mesh-terms algorithm. The following information was extracted from each publication during content analysis: diagnostic and treatment planning aspects of endodontic practice for which AI methods could be applied; accuracy levels registered for AI models used for different endodontic-related purposes; limitations of using AI within endodontic practice. Results. AI features could be used in endodontic practice for the following reasons: analysis of root canal morphology, identification of root fractures, verification of periapical lesions, estimation of root canal working length, root canal treatment planning, prediction of pain development during post-treatment period, predication of endodontic interventions success. The most prevalently used artificial intelligence methods for different endodontic diagnostic and treatment planning objectives were the following: convolutional neural network, artificial neurons network, case-based reasoning, deep learning, machine learning, neuro-fuzzy inference system, probabilistic neural network. Conclusion. Main advantage of using AI models in endodontic practice associated with improvement of diagnostic accuracy within reduced amount of time needed for X-ray images and clinical data analysis. AI application for apical foramen detection and working length determination demonstrates the highest level of accuracy compared to AI performance for other clinically related objectives in endodontics.Keywords
This publication has 27 references indexed in Scilit:
- Artificial Intelligence for the Computer-aided Detection of Periapical Lesions in Cone-beam Computed Tomographic ImagesJournal of Endodontics, 2020
- Artificial Intelligence in Dentistry: Chances and ChallengesJournal of Dental Research, 2020
- Evaluation of artificial intelligence for detecting periapical pathosis on cone‐beam computed tomography scansInternational Endodontic Journal, 2020
- Evaluation of an artificial intelligence system for detecting vertical root fracture on panoramic radiographyOral Radiology, 2019
- A deep-learning artificial intelligence system for assessment of root morphology of the mandibular first molar on panoramic radiographyDentomaxillofacial Radiology, 2019
- MeSH Now: automatic MeSH indexing at PubMed scale via learning to rankJournal of Biomedical Semantics, 2017
- Detection of vertical root fractures in intact and endodontically treated premolar teeth by designing a probabilistic neural network: an ex vivo studyDentomaxillofacial Radiology, 2017
- Meshable: searching PubMed abstracts by utilizing MeSH and MeSH-derived topical termsBioinformatics, 2016
- Retreatment Predictions in Odontology by means of CBR SystemsComputational Intelligence and Neuroscience, 2016
- How to improve your PubMed/MEDLINE searches: 3. advanced searching, MeSH and My NCBIJournal of Telemedicine and Telecare, 2014